Introduction to Computational Intelligence Paradigms

Computational Intelligence CHAPTER ONE :INTRODUCTION Alyaa Jaber Jalil

Syllabus Development of system intelligent( Concepts , models , algorithms and tools). Artificial Neural Networks. Genetic Algorithms. Fuzzy Systems. Swarm intelligence. Optimization and hybridization techniques.

Chapter 1 : Introduction to Computational Intelligence Computational Intelligence (CI) is a sub-branch of Artificial Intelligence (AI). CI focuses on mechanisms that exhibit an ability to learn or adapt to new situations, to generalize, abstract, discover and associate. CI includes: Artificial neural networks (NN). Evolutionary computation (EC). Swarm intelligence (SI). Artificial immune systems (AIS). Fuzzy systems (FS). .

Introduction to Computational Intelligence Each of the CI paradigms has its origins in biological systems. NNs model biological neural systems, EC models natural evolution, SI models the social behavior of organisms living in swarms or colonies, AIS models the human originated from studies of how organisms interact with their environment immune system, and FS

Introduction to Computational Intelligence AI S N N ES FS SI Probabilistic Techniques

Artificial Neural Networks Artificial mathematical models of human brain functions such as: perception, computation and memory. neural networks, refer to the The basic building blocks of biological neural systems are: nerve cells, referred to as neurons. A neuron consists of a cell body, dendrites and an axon.

Artificial Neural Networks Neurons are interconnected, where an interconnection is between the axon of one neuron and a dendrite of another neuron. This connection is referred to as a synapse. Signals propagate from the dendrites, through the cell body to the axon. A signal is transmitted to the axon of a neuron only when the cell fires . A neuron can either inhibit or excite a signal.

Artificial Neural Networks

Artificial Neural Networks An artificial neuron (AN) is a model of a biological neuron (BN). Each AN receives signals from the environment, or other ANs, gathers these signals, and when fired, transmits a signal to all connected ANs. Input signals are inhibited or excited through negative and positive numerical weights associated with each connection to the AN. The firing of an AN and the strength of the exiting signal are controlled via a function, referred to as the activation function. The AN collects all incoming signals, and computes a net input signal as a function of the respective weights. The net input signal serves as input to the activation function which calculates the output signal of the AN.

Artificial Neural Networks Weights . . . . . F(net) Output Signal Input Signals An artificial neural network (NN) is a layered network of ANs. An NN may consist of an input layer, hidden layers and an output layer. ANs in one layer are connected, fully or partially, to the ANs in the next layer. Feedback connections to previous layers are also possible.

Artificial Neural Networks

Artificial Neural Networks Several different NN types have been developed: Single-layer NNs, such as the Hopfield network. propagation, functional link and product unit networks. Multilayer feedforward NNs, for example, standard back- feature maps and the learning vector quantizer. Self-organizing NNs, such as the Kohonen self-organizing Combined supervised and unsupervised NNs, e.g. some radial basis function networks.

Artificial Neural Networks These NN types have been used for a wide range of applications, including: Diagnosis Of Diseases Speech Recognition Data Mining Composing Music Image Processing Forecasting Robot Control Credit Approval Classification Pattern Recognition Planning Game Strategies Compression, And Many Others

Evolutionary Computation Evolutionary processes from natural evolution, where the main concept is survival of the fittest: the weak must die. computation (EC) objects to mimic Evolutionary algorithms use a population of individuals, where an individual is referred to as a chromosome. A chromosome individuals in the population. defines the characteristics of Each characteristic is referred to as a gene. The value of a gene is referred to as an allele.

Evolutionary Computation For each generation, individuals compete to reproduce offspring. Those individuals capabilities have the best chance to reproduce. with the best survival Offspring are generated by combining parts of the parents, a process referred to as crossover. Each individual in the population can also undergo mutation which alters some of the allele of the chromosome. The survival strength of an individual is measured using a fitness function which reflects constraints of the problem to be solved. the objectives and

Evolutionary Computation After each generation, individuals may undergo culling, or individuals may survive to the next generation (referred to as elitism). Evolutionary algorithms include: Genetic Algorithms Genetic Programming Evolutionary Strategies Cultural Evolution

Swarm intelligence Swarm intelligence (SI) originated from the study of colonies, or swarms of social organisms. Particle swarm optimization (PSO) is a population-based search procedure where the individuals, referred to as particles, are grouped into a swarm. Each particle in the swarm represents a candidate solution to the optimization problem. In a PSO system, each particle is flown through the multidimensional search space, adjusting its position in search space according to its own experience and that of neighboring particles.

Swarm intelligence A particle therefore makes use of the best position encountered by itself and the best position of its neighbors to position itself toward an optimum solution. The performance of each particle is measured according to a predefined fitness function which is related to the problem being solved. Applications of PSO include: Function Approximation Clustering Optimization Of Mechanical Structures Solving Systems Of Equations.

Fuzzy Systems Traditional set theory requires elements to be either part of a set or not. Human reasoning is, however, almost always not this exact. Our observations and reasoning usually include a measure of uncertainty. For example, humans are capable of understanding the sentence: Some Computer Science students can program in most languages . But how can a computer represent and reason with this fact?

Fuzzy Systems Fuzzy sets and fuzzy logic allow what is referred to as approximate reasoning. With fuzzy sets, an element belongs to a set to a certain degree of certainty. Fuzzy logic allows reasoning with these uncertain facts to infer new facts, with associated with each fact. a degree of certainty Fuzzy systems have been applied successfully to control systems, gear transmission and braking systems in vehicles, controlling lifts, home appliances, controlling traffic signals, and many others.

Any Question??